© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16405
    Prev
    Next
    INDEX
    Explanations

    following procedural steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.15
     dianteira
    -1.11
     stycz
    -1.03
    vention
    -1.03
     reflexión
    -1.02
     amenaza
    -1.00
     kwiet
    -1.00
     SALUD
    -1.00
     ramach
    -0.97
     многих
    -0.96
    POSITIVE LOGITS
     immediately
    1.17
     proceed
    0.99
     then
    0.98
     followed
    0.95
     seguida
    0.92
     roche
    0.90
     rồi
    0.89
     gypsy
    0.89
     gently
    0.89
     corse
    0.87
    Activations Density 0.007%

    No Known Activations